Lukas Galke Poech's picture

Lukas Galke Poech

lgalke

·

https://lgalke.github.io

AI & ML interests

LLM interpretability, agentic/multi-agent safety

Recent Activity

liked a model 3 days ago

syvai/hviske-v3-conversation

authored a paper 4 days ago

Confidence and Calibration of Activation Oracles for Reliable Interpretation of Language Model Internals

upvoted a paper 5 days ago

Confidence and Calibration of Activation Oracles for Reliable Interpretation of Language Model Internals

View all activity

Organizations

lgalke 's models 1

lgalke/Qwen3.5-35B-A3B-psysafe

Image-Text-to-Text • 36B • Updated Mar 25 • 69